feat(coder): v2.6 Phase 3 — lifecycle hardening (idle evict, crash recovery, worktree reaper)

Idle TTL eviction per (chat,agent) + LRU cap (never a busy backend); pure lifecycle-decisions.ts (TDD). Crash recovery lifts openchamber's health-monitor + busy-aware-restart + stale-grace state machine into opencode-server.ts (+ port reclaim) and warm-acp.ts; opencode crash -> fresh sessions, ACP -> re-session/new. F.1 turn-guard + U.6 usage preserved (their tests pass). Orphan worktree reaper (1h grace, superset-style dirty/unpushed preflight, Paseo soft-delete) + close hooks + diff re-baseline after apply_pending. 35 new tests + DB-opt-in reconnect test; 215 coder tests pass; tsc + build clean. Completes v2.6. Follow-ups out of scope: apps/server close-hook caller, 3.7 DiffPanel staging hint, live smokes.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/coder/src/routes/lifecycle.ts

@@ -0,0 +1,122 @@
+/**
+ * v2.6 Phase 3 (3.3) — chat/session close-or-archive cleanup hook (coder side).
+ *
+ * Chat/session close + archive + delete all live in apps/server (Docker), which
+ * cannot see the host worktree dirs (/tmp/booworktrees), run git on them, or reach
+ * the warm agent processes the dispatcher pooled in THIS (host systemd) process. So
+ * — exactly like the `worktree-risk` guard — the server signals the coder when a
+ * chat/session closes, and the coder does the real teardown:
+ *   1. dispose the chat's warm-ACP backends (`agentPool.closeChat`) — kills the
+ *      goose/qwen child processes for that chat,
+ *   2. close the chat's opencode session on the shared server (`closeSession`),
+ *   3. mark every `agent_sessions` row for the chat 'closed' + (when the session's
+ *      last open chat closes) remove the shared session worktree, preflighting
+ *      work-at-risk so uncommitted/unmerged work is never silently dropped
+ *      (`closeChatBackendState`).
+ *
+ * Idempotent: closing an already-closed chat is a no-op (0 rows, no backend).
+ *
+ * SERVER WIRING (not done here — apps/server, out of this batch's scope): the
+ * server's `POST /api/chats/:id/archive`, `DELETE /api/chats/:id`, and the
+ * session archive/delete routes should fire-and-forget
+ *   fetch(`${BOOCODER_URL}/api/chats/${id}/close`, { method: 'POST' })
+ * after publishing their WS frame (best-effort; the orphan-worktree reaper +
+ * idle-pool eviction are the backstop if the call is missed).
+ */
+import type { FastifyInstance } from 'fastify';
+import type { Sql } from '../db.js';
+import { agentPool, OPENCODE_POOL_KEY } from '../services/agent-pool.js';
+import { closeChatBackendState } from '../services/worktrees.js';
+import type { AgentSessionHandle } from '../services/agent-backend.js';
+
+export function registerLifecycleRoutes(app: FastifyInstance, sql: Sql): void {
+  // POST /api/chats/:chatId/close — tear down all warm state for a chat tab.
+  app.post<{ Params: { chatId: string }; Querystring: { force?: string } }>(
+    '/api/chats/:chatId/close',
+    async (req) => {
+      const chatId = req.params.chatId;
+      const force = req.query.force === 'true' || req.query.force === '1';
+
+      // 1. Close the chat's opencode session on the SHARED server (the server is
+      //    not chat-keyed, so agentPool.closeChat won't touch it). Resolve the
+      //    stored opencode session id and ask the backend to drop it.
+      const ocRows = await sql<{ agent: string; agent_session_id: string | null; worktree_id: string | null; session_id: string | null }[]>`
+        SELECT agent, agent_session_id, worktree_id, session_id
+        FROM agent_sessions
+        WHERE chat_id = ${chatId} AND backend = 'opencode_server'
+      `;
+      const ocBackend = agentPool.peek(OPENCODE_POOL_KEY, 'opencode');
+      if (ocBackend) {
+        for (const row of ocRows) {
+          if (!row.agent_session_id) continue;
+          const handle: AgentSessionHandle = {
+            sessionId: row.session_id ?? '',
+            agent: row.agent,
+            backend: 'opencode_server',
+            chatId,
+            worktreeId: row.worktree_id ?? '',
+            agentSessionId: row.agent_session_id,
+            serverPort: null,
+          };
+          await ocBackend.closeSession(handle).catch((err) => {
+            app.log.warn({ err: err instanceof Error ? err.message : String(err), chatId }, 'lifecycle: opencode closeSession threw');
+          });
+        }
+      }
+
+      // 2. Dispose any warm-ACP backends pooled under this chat (kills the
+      //    goose/qwen child + marks its agent row closed via the backend).
+      const disposed = await agentPool.closeChat(chatId);
+
+      // 3. DB + worktree truth: mark agent rows closed; remove the shared session
+      //    worktree iff this was the session's last open chat (preflight at-risk).
+      const result = await closeChatBackendState(sql, chatId, { force });
+
+      app.log.info({ chatId, disposed, ...result }, 'lifecycle: chat closed');
+      return { ok: true, disposed, ...result };
+    },
+  );
+
+  // POST /api/sessions/:sessionId/close — close every open chat in a session
+  // (session archive/delete). Loops the chat-close path so the same preflight +
+  // teardown applies per chat; the worktree is removed on the last one.
+  app.post<{ Params: { sessionId: string }; Querystring: { force?: string } }>(
+    '/api/sessions/:sessionId/close',
+    async (req) => {
+      const sessionId = req.params.sessionId;
+      const force = req.query.force === 'true' || req.query.force === '1';
+
+      const chats = await sql<{ id: string }[]>`
+        SELECT id FROM chats WHERE session_id = ${sessionId}
+      `;
+      const results: { chatId: string; disposed: string[]; worktreeRemoved: boolean; worktreeAtRisk: boolean }[] = [];
+      for (const c of chats) {
+        const ocBackend = agentPool.peek(OPENCODE_POOL_KEY, 'opencode');
+        if (ocBackend) {
+          const ocRows = await sql<{ agent: string; agent_session_id: string | null; worktree_id: string | null; session_id: string | null }[]>`
+            SELECT agent, agent_session_id, worktree_id, session_id
+            FROM agent_sessions WHERE chat_id = ${c.id} AND backend = 'opencode_server'
+          `;
+          for (const row of ocRows) {
+            if (!row.agent_session_id) continue;
+            await ocBackend.closeSession({
+              sessionId: row.session_id ?? '',
+              agent: row.agent,
+              backend: 'opencode_server',
+              chatId: c.id,
+              worktreeId: row.worktree_id ?? '',
+              agentSessionId: row.agent_session_id,
+              serverPort: null,
+            }).catch(() => {});
+          }
+        }
+        const disposed = await agentPool.closeChat(c.id);
+        const r = await closeChatBackendState(sql, c.id, { force });
+        results.push({ chatId: c.id, disposed, worktreeRemoved: r.worktreeRemoved, worktreeAtRisk: r.worktreeAtRisk });
+      }
+
+      app.log.info({ sessionId, chats: results.length }, 'lifecycle: session closed');
+      return { ok: true, results };
+    },
+  );
+}

apps/coder/src/routes/pending.ts

@@ -10,6 +10,7 @@ import {
   queueCreate,
 } from '../services/pending_changes.js';
 import { WriteGuardError } from '../services/write_guard.js';
+import { rebaselineWorktreeAfterApply } from '../services/worktrees.js';
 
 const CreateBody = z.object({
   file_path: z.string().min(1),
@@ -117,6 +118,15 @@ export function registerPendingRoutes(app: FastifyInstance, sql: Sql): void {
       }
 
       const results = await applyAll(sql, sessionId, projectRoot);
+
+      // v2.6 Phase 3 (3.5): re-baseline the session worktree's diff to the applied
+      // state, so the next external-agent turn diffs against applied-not-original
+      // and doesn't re-surface the just-applied changes. Best-effort: a worktree
+      // session may not exist (native-only chat), and a re-baseline hiccup must not
+      // fail the apply the user just requested.
+      if (results.some((r) => r.success)) {
+        await rebaselineWorktreeAfterApply(sql, sessionId).catch(() => {});
+      }
       return { results };
     },
   );
@@ -136,6 +146,15 @@ export function registerPendingRoutes(app: FastifyInstance, sql: Sql): void {
       const result = await applyOne(sql, changeId, projectRoot);
       if (!result.success) {
         reply.code(422);
+      } else {
+        // v2.6 Phase 3 (3.5): re-baseline the session worktree after a successful
+        // apply so the next external-agent turn diffs against applied-not-original.
+        // Resolve the change's session; best-effort, never fails the apply.
+        const sessRows = await sql<{ session_id: string }[]>`
+          SELECT session_id FROM pending_changes WHERE id = ${changeId}
+        `;
+        const sessionId = sessRows[0]?.session_id;
+        if (sessionId) await rebaselineWorktreeAfterApply(sql, sessionId).catch(() => {});
       }
       return result;
     },